© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 1465
    Prev
    Next
    INDEX
    Explanations

    words related to sketches or sketching activities

    oai_token-act-pair · gpt-3.5-turbo

    references to sketches and sketch-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iod
    -0.77
     Britann
    -0.74
    onso
    -0.73
    aceutical
    -0.71
     Rated
    -0.64
     Malfoy
    -0.64
     Fenrir
    -0.64
    onte
    -0.62
     bom
    -0.60
     Unsure
    -0.60
    POSITIVE LOGITS
    eers
    0.90
     Sketch
    0.87
     sketch
    0.85
    BOOK
    0.80
    song
    0.77
    ket
    0.77
    izable
    0.77
    lings
    0.76
    eenth
    0.76
    ival
    0.75
    Activations Density 0.137%

    No Known Activations